© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13632
    Prev
    Next
    INDEX
    Explanations

    CPU

    np_acts-logits-general · gemini-2.5-flash-lite

    code and finance related tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wiss
    0.36
     imprisoned
    0.33
     deliverance
    0.33
     ک
    0.32
     instill
    0.32
     bombard
    0.32
     envió
    0.32
     repris
    0.31
     exhort
    0.31
     sculptures
    0.30
    POSITIVE LOGITS
    (),
    0.39
    itipi
    0.38
    \":
    0.38
    rafpunkte
    0.37
    filter
    0.36
    intersection
    0.36
     тобто
    0.36
    align
    0.35
    终止
    0.35
    ──
    0.35
    Activations Density 0.021%

    No Known Activations